35 results about "Patient input" patented technology

The invention relates to a patient examination item recommendation method based on a medical knowledge graph. The method comprises the steps that firstly, historical data in the medical field is acquired, key information is extracted from the historical data to generate an entity relation triple, and then a medical knowledge graph is constructed; then, generating a patient state sub-graph based on patient input information, processing the medical knowledge graph by adopting an improved TransD model, and determining unique representation of an entity-relationship pair; mapping the patient state sub-map to a unique representation space, obtaining vector representation of a patient and an examination item related entity, and calculating a similarity value between vectors to obtain a similarity value matrix; and finally, performing priority ranking on the inspection items according to the matrix, and generating a final recommendation list through threshold screening and combination with graph neural network verification, optimization and adjustment of priorities. By adopting the method, examination items can be accurately recommended for patients, doctors are assisted to improve the treatment efficiency, the queuing time of the patients is shortened, and the medical experience of the patients is remarkably improved.

The invention discloses a traditional Chinese medicine syndrome and prescription matching recommendation method based on a graph neural network. The method comprises the following steps: S1, establishing a traditional Chinese medicine knowledge graph containing a node and edge relationship; s2, performing data preprocessing on the traditional Chinese medicine knowledge graph; s3, generating feature vectors of syndrome nodes and feature vectors of prescription nodes; s4, mapping the syndrome information of the patient to the generated feature vector space; s5, generating a prescription matching candidate set; s6, finally determining an optimal prescription combination; and S7, based on the optimized optimal prescription combination, outputting a prescription recommendation result containing prescription composition, medicinal material dosage and indication description, and carrying out interpretability analysis on the recommendation result. According to the method, the high-precision matching of the patient input features and the prescription features is realized, the potential semantic relationship in the traditional Chinese medicine knowledge graph can be more accurately captured, and the matching precision is remarkably improved.

The invention discloses a traditional Chinese medicine intelligent diagnosis and treatment platform construction method based on combination of a large model and two-channel retrieval, the diagnosis and treatment platform is used for inputting and outputting traditional Chinese medicine diagnosis and treatment suggestions according to a patient based on a traditional Chinese medicine knowledge graph, and the method comprises the following steps: step S1, collecting clinical medical record data and preprocessing the data; s2, constructing a traditional Chinese medicine knowledge graph based on a large language model; s3, constructing a traditional Chinese medicine prescription model based on a two-channel retrieval mechanism by fusing the large language model and the traditional Chinese medicine knowledge graph; s4, performing fusion processing on the dual-channel information retrieval result, and outputting a prescription after comprehensive reasoning; and S5, matching the model generation prescription with a clinical famous doctor prescription, and verifying the accuracy of the traditional Chinese medicine prescription model. The famous doctor intelligent inheriting cloud platform is constructed, the effects of remarkably improving inheriting efficiency and breaking through traditional Chinese medicine diagnosis and treatment standardization are achieved, and a good foundation is laid for subsequent famous doctor intelligent inheriting product landing popularization.

The application relates to the technical field of human resource management, in particular to a medical staff scheduling system based on medical staff skills, which comprises a standard skill input and classification device, which is used for inputting the working skills of each department, dividing the same working skills of each department into general skills, and dividing the special working skills of each department into special skills; a department patient input device, which obtains the treatment information of patients in each department ward, extracts the predicted workload of each patient in the next scheduling cycle, and counts the predicted workload of each department; the predicted workload comprises the execution times of each general skill and the execution times of each special skill; the system realizes cross-department dynamic scheduling by constructing a hospital-level skill resource pool and a demand prediction mechanism, standardizes the general skills into shared resources, and enables medical staff to flexibly support departments with high demand peaks.

The invention relates to a computer-implemented method for determining spatially resolved radiation load information of a patient when conducting an examination with an imaging X-ray apparatus having an X-ray radiator for outputting an X-ray field for conducting the examination, wherein patient input dose information is determined for determining the radiation load information, wherein the pre-dose information is determined in the case of use of a matching filter arranged between the patient and the X-ray radiator, which causes a non-uniform dose distribution in a plane perpendicular to a central ray of the X-ray field, the pre-dose information describing a uniform distribution of the X-ray dose acting on the patient without the matching filter; dose distribution information is calculated using the pre-dose information by means of a filter model, which describes at least the dose distribution of the X-ray dose acting on the patient in the part of the X-ray field covered by the matching filter; and the patient input dose information is determined using the dose distribution information.

The utility model discloses a hepatobiliary double-headed infusion apparatus, which relates to the technical field of medical infusion apparatuses, and comprises a first liquid inlet tube, a second liquid inlet tube, a conduit, two temporary storage buckets, a first liquid inlet tube, a second liquid inlet tube, a second liquid inlet tube, a second liquid inlet tube, a second liquid inlet tube, a third liquid inlet tube and a fourth liquid inlet tube, the two temporary storage hoppers are respectively communicated with the first liquid inlet pipe and the second liquid inlet pipe; the detection assembly is mounted on the outer surfaces of the dripping bucket and the temporary storage bucket, and the detection mechanism is used for detecting liquid level changes in the dripping bucket and the temporary storage bucket; and the control mechanism is arranged above the temporary storage hopper, and the control mechanism comprises a control assembly and a stopping assembly. Through the arrangement of the detection assembly and the control mechanism, after one bottle of liquid medicine is completely infused, another bottle of liquid medicine can be automatically infused for a patient, and therefore the problem that the infusion bottle cannot be replaced in time when the patient lacks action force and is unattended is solved.

The following relates generally to improved clinical symptom analysis. In some embodiments, one or more processors: (1) receive patient input data; (2) obtain patient survey data representing the patient's condition; (3) determine a trend in the patient survey data using a determination algorithm; (4) apply the generative AI algorithm to the patient input data, the patient survey data, and the trend in the patient survey data to produce a report of the trend of the patient's condition; and / or (5) display the report on a display device.

Methods and systems for providing context for alarms and resolving alarms using a virtual agent are described. Inputs including imaging, patient information, and aural, visual, and mechanical patient inputs are analyzed to provide context for an alarm. Based on the context, the methods and systems may identify a patient action that may resolve the alarm. A virtual agent may interact with the patient to identify and resolve the alarm without additional caregiver input.

Methods and systems for providing context for alarms and resolving alarms using a virtual agent are described. Inputs including imaging, patient information, and aural, visual, and mechanical patient inputs are analyzed to provide context for an alarm. Based on the context, the methods and systems may identify a patient action that may resolve the alarm. A virtual agent may interact with the patient to identify and resolve the alarm without additional caregiver input.

A system is provided.SOLUTION: A system comprising: means for inputting symptom information from a patient before a visit; means for analyzing the input symptom information and searching for an appropriate medical institution or medical worker; means for presenting information on a plurality of medical institutions or medical workers based on the analysis result and allowing the patient to make a selection; means for confirming an appointment with the selected medical institution or medical worker; and means for storing the patient's medical data as electronic data and sharing the data among medical institutions.SELECTED DRAWING: Figure 1

A system and method to collect feedback data from a patient wearing an interface such as a mask when using a respiratory pressure therapy device such as a CPAP device. The system includes a storage device including a facial image of the patient. An interface in communication with the respiratory pressure therapy device collect operational data from when the patient uses the interface. A patient interface collects subjective patient input data from the patient in relation to the patient interface. An analysis module correlates a characteristic of the interface with the facial image data, operational data and subjective patient input data.

The following relates generally to improved clinical symptom analysis. In some embodiments, one or more processors: (1) receive patient input data; (2) obtain patient survey data representing the patient's condition: (3) determine a trend in the patient survey data using a determination algorithm; (4) apply the generative Al algorithm to the patient input data, the patient survey data, and the trend in the patient survey data to produce a report of the trend of the patient's condition; and / or (5) display the report on a display device.

A system and method of collecting feedback data from a patient wearing an interface such as a mask while using a respiratory pressure therapy device such as a CPAP device. The system includes a storage device including a facial image of the patient. An interface in communication with the respiratory pressure therapy device, the interface collecting operational data from the patient while using the interface. The patient interface collects subjective patient input data from the patient regarding the patient interface. An analysis module correlates features of the interface with the facial image data, the operational data, and the subjective patient input data.

The application provides a method and device for training a model, and a method and device for predicting a sub-diagnosis intention. An electronic device supports obtaining a target main diagnosis intention of a patient in a process of queuing for diagnosis, and predicting and outputting, based on a prediction model of a sub-diagnosis intention, a sub-diagnosis intention in which a patient inputs a sub-named entity from a plurality of sub-diagnosis intentions cascaded with the target main diagnosis intention, so that the patient can input a sub-named entity to the output sub-diagnosis intention, to collect answers of the patient to questions in advance automatically by using time of the patient in the process of queuing for diagnosis, and facilitate automatic recording of a disease of the patient, so as to avoid omission and misdiagnosis or missed diagnosis. Furthermore, after the patient enters a diagnosis stage, a doctor can directly obtain answers of the patient to questions, without real-time questioning of the patient by the doctor, so as to save time of the doctor and the patient in the process of diagnosis.

To provide an information processing system that can improve communication between patients and healthcare professionals. [Solution] The information processing system comprises: a pre-information acquisition means for acquiring patient information based on patient input; a prescription pattern determination means for determining one of a plurality of prescription patterns based on the pre-information acquisition means; a questionnaire generation means for generating a questionnaire corresponding to the prescription pattern determined by the prescription pattern determination means; a questionnaire result acquisition means for acquiring the patient's response results to the questionnaire generated by the questionnaire generation means; a supplementary explanation generation means for generating supplementary explanations for the patient based on the response results acquired by the questionnaire result acquisition means; and a feedback generation means for generating feedback for healthcare professionals based on the response results acquired by the questionnaire result acquisition means.

The invention discloses an input and output monitoring and early warning system and method based on multi-modal data fusion, and the system comprises an input and output data collection module which is used for collecting input data and output data of a patient; the local processing module is used for storing the collected input data and output data in local equipment of the patient and preprocessing the input data and the output data to obtain categories, water content and confidence of the input and output of the patient; the data processing module is used for carrying out secondary processing on the data of which the confidence is lower than a preset confidence threshold to obtain water content correction results of the input and output of the patient, and generating a patient input and output report; and the early warning module is used for obtaining the patient input and output report and sending out early warning to the patient and medical care. According to the invention, the comprehensiveness, accuracy and patient compliance of data acquisition can be improved, so that accurate input and output prediction and personalized analysis are realized, a more scientific basis is provided for clinical treatment, and the treatment effect is improved.

A method comprises establishing communication between a therapy device implantable in a patient and a consumer electronic device operable by the patient. The method comprises controlling, by the consumer electronic device, a predetermined set of therapy device functions in response to patient inputs to the consumer electronic device. The method also comprises transmitting therapy data from the therapy device to the consumer electronic device. The method further comprises presenting therapy data on a display of the consumer electronic device.

A decision support system that aids healthcare practitioners in making more informed clinical decisions and avoiding errors related to diagnosis and treatment of diseases. The system utilizes several data points from the patient history and clinical findings input by the patient and the doctor, to help the doctor make a more accurate diagnosis and develop a more informed treatment plan that incorporates not just drugs and procedures, but also dietary and lifestyle interventions. A system of the present disclosure comprises dosage calculator, symptom checker, differential diagnosis, drug interaction checker, side effect checker, nutritional analyzer and drug-food interaction checker input pathways and corresponding database compartments. Output data is generated in correspondence with patient input data and stored on a database server, where it is correlated with patient outcomes over time and improved through machine learning.

A system is provided.SOLUTION: A system comprising: means for receiving patient-input information; means for generating a response based on the received input information using a generative AI model; means for receiving patient-physiological information from a healthcare device; and means for analyzing the received physiological information and providing results to the subject.SELECTED DRAWING: Figure 1

Example devices, systems, and techniques are described for determining a current blood pressure for a potential syncope episode. An example system includes processing circuitry configured to determine an occurrence of a potential syncope episode. To determine the occurrence of the potential syncope episode, the processing circuitry is configured to determine at least one of a) entering of patient input on an external device indicative of one or more patient symptoms of syncope, b) changes in a sensed neurological signal, or c) occurrence of a sensed sound of emesis. The processing circuitry is configured to determine, based on the determination of the occurrence of the potential syncope episode, a current blood pressure. The processing circuitry is configured to output an indication of the potential syncope episode and an indication of the current blood pressure.

A computer-program product, system, and method of retrieving electronic health records (EHRs) of a patient including: requesting legally compliant permission from a patient to access a plurality of EHRs of the patient from a plurality of separate electronic storage devices storing at least one of the EHRs of the patient in a non-transitory computer-readable recording medium; receiving an access request from the patient via a natural language interface to retrieve the EHRs of the patient from the separate electronic storage devices; processing the access request using a generative artificial intelligence (AI) model having a unique licensing number assigned thereto; generating via the AI model a structured access request query; and sending via a communication network the structured access request query with the legally compliant permission to the separate electronic storage devices and thereby retrieving the EHRs.

A system and method to collect feedback data from a patient wearing an interface such as a mask when using a respiratory pressure therapy device such as a CPAP device. The system includes a storage device including a facial image of the patient. An interface in communication with the respiratory pressure therapy device collect operational data from when the patient uses the interface. A patient interface collects subjective patient input data from the patient in relation to the patient interface. An analysis module correlates a characteristic of the interface with the facial image data, operational data and subjective patient input data.

A system includes processing circuitry configured to: receive a first signal via sensing circuitry of the system, the first signal representing a first evoked electrical signal induced by an electrical stimulation delivered during a posture state of a patient; determining a first signal characteristic of the first evoked electrical signal; receiving a patient input via one or more user devices of the system, the patient input indicating a comfort level of the patient associated with the first evoked electrical signal; determining a target characteristic of the posture state based on the first signal characteristic and the patient input; receiving a second signal via the sensing circuit, the second signal representing a second evoked electrical signal induced by the electrical stimulation delivered during the gestural state; and control one or more parameters based on a second signal characteristic of the second evoked electrical signal and the target characteristic, the one or more parameters at least partially defining subsequent delivery of the electrical stimulation.

An electronic device for de-identifying personal information in clinical information text according to an embodiment comprises: a memory; and a processor for training a machine learning-based de-identification tag generation model on the basis of annotation data indicating a de-identification category for each token of training text and a training dataset including the training text, providing clinical information text for a patient input by medical personnel to the trained de-identification tag generation model, so as to output a de-identification category for each token of the clinical information text, and changing a token corresponding to personal information in the clinical information text into an expression indicating non-personal information on the basis of the output de-identification category.

The invention relates to the technical field of augmented reality, and discloses a medical data dynamic minimization secure channel construction method based on an accompanying diagnosis scene, and the method comprises the steps: obtaining an operation event of the accompanying diagnosis scene and patient input data; identifying an intention conflict node between a medical care operation intention in the operation event and a privacy appeal in the patient input data; separating necessary data and redundant data in the intention conflict node to obtain a minimum data demand of the accompanying diagnosis scene; according to the minimum data demand, configuring a secure transmission link of the accompanying diagnosis scene, and identifying a key evolution point of the minimum data demand; monitoring medical data missing items in the accompanying diagnosis scene, and mapping the medical data missing items to the key evolution points; by combining the execution result of the mapping, the problem that the contradictory coupling characteristic of medical care diagnosis and treatment requirements and patient privacy protection in the accompanying diagnosis scene is not considered in the prior art can be solved.

The present disclosure generally relates to a computer system (100) and a computerized method (300) for predicting a renal condition of a patient using a machine learning model (200). The method (300) comprises: obtaining (310, 330) a current patient input dataset and a historical eGFR input dataset associated with a patient; generating (320) a patient input vector representation (222) using the current patient input dataset and the input linear layer (220); generating (340) an eGFR vector representation (242) using the historical eGFR input dataset and a first input machine learning module (240); splicing (350) the patient input vector representation and the eGFR vector representation (222, 242) into an output vector representation (260); and generating (360) a predictive output (280) using the output vector representation (260) and an output machine learning module (270), the predictive output (280) including a risk assessment of a patient having a renal condition.

A wearable medical system (WMS) includes a dongle having a cable, cancel switch, microphone, and processor. The processor determines, based on patient input, whether a shock criterion is met and, if met, causes an output device to provide a human-perceptible indication (HPI). After a preset delay following the HPI, the processor discharges stored electrical charge through a therapy electrode to deliver a shock to a patient if the cancel switch has not been actuated. If the cancel switch is actuated within the preset delay, discharge of the stored electrical charge is prevented.

Disclosed herein are methods, devices, and systems for the enhanced monitoring of visual function via telemedicine to detect early onset of changes and abnormalities associated with disease. The systems include a cloud environment or neural network communicating various tests and images to a client device in which a user / patient is properly positioned to view a display of the client device, receive stimuli, and provide patient input which is evaluated in terms of timing and substance to generate a contrast-sensitivity map of a visual function for the patient. Various ocular tests are described for implementation in a new home-based computer environment rather than using expensive and specific medical equipment in a doctor's office.

In certain embodiments, a system for assessing a float in an eye of a patient includes a display device, an input device, and a computer. The display device displays a target and a background. The background has an alignment point and an alignment axis. An eye axis of the eye is substantially aligned with the alignment axis when the eye is gazing at the alignment point. The input device receives patient input from a patient. The computer provides a target display input to the display device to generate a target that moves according to the pattern for the eye to follow. When the eye follows the moving target, the eye axis moves relative to the alignment axis. The computer records patient input indicating that the patient sees the float. The computer calculates a severity score indicative of the severity of the float from the patient input and generates a report describing the severity score.

This disclosure relates to systems and methods for managing patients of knee surgeries. A pre-operative patient questionnaire user interface is associated with a future knee operation of the patient. Patient input data is indicative of answers of a patient in relation to the pre-operative patient questionnaire. A processor of a computer system evaluates a statistical model to determine a predicted satisfaction value indicative of satisfaction of the patient with the future knee operation. The statistical model comprises nodes stored on data memory representing the patient input data and the predicted satisfaction value, and edges stored on data memory between the nodes representing conditional dependencies between the patient input data and the predicted satisfaction value. The processor then generates an electronic document comprising a surgeon report associated with the future knee operation to indicate to the surgeon the predicted satisfaction value.